conference-paper
Evaluating Human-AI Hybrid Conversational Systems with Chatbot Message Suggestions
Research footprint
At a glance
- الاستشهادات
- 26
- المراجع
- 63
- Comments
- 0
Paper overview
Abstract
AI chatbots can offer suggestions to help humans answer questions by reducing text entry effort and providing relevant knowledge for unfamiliar questions. We study whether chatbot suggestions can help people answer knowledge-demanding questions in a conversation and influence response quality and efficiency. We conducted a large-scale crowdsourcing user study and evaluated 20 hybrid system variants and a human-only baseline. The hybrid systems used four chatbots of varied response quality and differed in the number of suggestions and whether to preset the message box with top suggestions.
Record transparency
Publication details
- DOI
- 10.1145/3459637.3482340
- OpenAlex
- W3209067643
- Document type
- conference-paper
- Language
- EN
- Last metadata update
Comments
تسجيل الدخول للانضمام إلى النقاش.